### Clone Repository and Install Dependencies

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/README.md

Clone the repository and install project dependencies using npm. This is the first step for direct local setup.

```bash
git clone https://github.com/iBUHub/AIStudioToAPI.git
cd AIStudioToAPI
```

```bash
npm install
```

--------------------------------

### Start the API Service

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/README.md

Start the API service after setup. The service will be accessible at http://localhost:7860, and a web console is available at the same address for monitoring.

```bash
npm start
```

--------------------------------

### Get System Status

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Retrieve detailed system status information, including account details, configuration, and active contexts. Requires authentication.

```bash
curl http://localhost:2048/api/status \
  -H "Authorization: Bearer your-api-key"
```

--------------------------------

### OpenAI Chat Completions with Function Calling

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Example of a chat completion request that includes tool definitions for function calling. The 'tool_choice' parameter controls whether the model should call a function.

```bash
curl -X POST http://localhost:2048/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
    "model": "gemini-2.5-flash",
    "messages": [
      {"role": "user", "content": "北京今天的天气怎么样？"}
    ],
    "tools": [
      {
        "type": "function",
        "function": {
          "name": "get_weather",
          "description": "获取指定城市的天气信息",
          "parameters": {
            "type": "object",
            "properties": {
              "city": {
                "type": "string",
                "description": "城市名称"
              }
            },
            "required": ["city"]
          }
        }
      }
    ],
    "tool_choice": "auto" 
  }'
```

--------------------------------

### List Models (OpenAI Compatible)

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/README.md

Use this GET endpoint to retrieve a list of available models compatible with the OpenAI API format.

```http
GET /v1/models
```

--------------------------------

### Generate TTS with cURL

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/docs/zh/api-examples.md

Examples for generating audio from text using default settings, specific voices, or multi-speaker configurations.

```bash
curl -X POST http://localhost:7860/v1beta/models/gemini-2.5-flash-preview-tts:generateContent \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key-1" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {
            "text": "你好，这是一个语音合成测试。"
          }
        ]
      }
    ],
    "generationConfig": {
      "responseModalities": ["AUDIO"]
    }
  }'
```

```bash
curl -X POST http://localhost:7860/v1beta/models/gemini-2.5-flash-preview-tts:generateContent \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key-1" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {
            "text": "你好，这是一个语音合成测试。"
          }
        ]
      }
    ],
    "generationConfig": {
      "responseModalities": ["AUDIO"],
      "speechConfig": {
        "voiceConfig": {
          "prebuiltVoiceConfig": {
            "voiceName": "Kore"
          }
        }
      }
    }
  }'
```

```bash
curl -X POST http://localhost:7860/v1beta/models/gemini-2.5-flash-preview-tts:generateContent \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key-1" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {
            "text": "TTS the following conversation between Joe and Jane:\nJoe: How are you today Jane?\nJane: I am doing great, thanks for asking!"
          }
        ]
      }
    ],
    "generationConfig": {
      "responseModalities": ["AUDIO"],
      "speechConfig": {
        "multiSpeakerVoiceConfig": {
          "speakerVoiceConfigs": [
            {
              "speaker": "Joe",
              "voiceConfig": {
                "prebuiltVoiceConfig": {
                  "voiceName": "Charon"
                }
              }
            },
            {
              "speaker": "Jane",
              "voiceConfig": {
                "prebuiltVoiceConfig": {
                  "voiceName": "Kore"
                }
              }
            }
          ]
        }
      }
    }
  }'
```

--------------------------------

### Health Check Response Example

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

An example of the JSON response received from the health check endpoint, indicating the server's status.

```json
{
  "status": "ok",
  "browserConnected": true,
  "uptime": 3600.123,
  "timestamp": "2025-01-15 10:30:45.123 [Asia/Shanghai]"
}
```

--------------------------------

### Anthropic Claude Messages Request with Thinking Mode

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Example of a messages request that enables 'Thinking Mode' for more complex reasoning. Specify the 'budget_tokens' to control the thinking process.

```bash
curl -X POST http://localhost:2048/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: your-api-key" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "gemini-2.5-pro",
    "max_tokens": 16000,
    "thinking": {
      "type": "enabled",
      "budget_tokens": 10000
    },
    "messages": [
      {"role": "user", "content": "设计一个高并发的分布式系统架构"}
    ]
  }'
```

--------------------------------

### Run Docker Container (Command Line)

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/README.md

Deploy the service using a Docker command. This command maps the host port 7860 to the container port, mounts a volume for authentication files, and sets environment variables for API keys and timezone.

```bash
docker run -d \
  --name aistudio-to-api \
  -p 7860:7860 \
  -v /path/to/auth:/app/configs/auth \
  -e API_KEYS=your-api-key-1,your-api-key-2 \
  -e TZ=Asia/Shanghai \
  --restart unless-stopped \
  ghcr.io/ibuhub/aistudio-to-api:latest
```

--------------------------------

### 运行自动登录脚本

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/docs/zh/auto-fill-guide.md

执行 npm 命令启动账号设置脚本，根据控制台提示选择账号进行自动填充。

```bash
npm run setup-auth
```

--------------------------------

### Create Response with Reasoning Configuration

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

This endpoint allows for response generation with specific reasoning configurations, such as setting the effort level.

```bash
curl -X POST http://localhost:2048/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
    "model": "gemini-2.5-pro",
    "input": "设计一个电商系统的数据库架构",
    "reasoning": {
      "effort": "high"
    }
  }'
```

--------------------------------

### 启用 Nginx 配置

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/docs/zh/nginx-setup.md

通过创建符号链接并重启服务来应用 Nginx 配置。

```bash
# 创建符号链接以启用站点
sudo ln -s /etc/nginx/sites-available/aistudio-api /etc/nginx/sites-enabled/

# 检查一下配置是否正确
sudo nginx -t

# 重启 Nginx
sudo systemctl restart nginx
```

--------------------------------

### 配置账号 CSV 文件

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/docs/zh/auto-fill-guide.md

在项目根目录创建 users.csv 文件，按 email 和 password 的格式存储账号信息。

```csv
email,password
your-email-1@gmail.com,your-password-1
your-email-2@gmail.com,your-password-2
```

--------------------------------

### Build Docker Image from Source

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/README.md

Build a custom Docker image from the project's source code. This allows for local image creation before running the container.

```bash
docker build -t aistudio-to-api .
```

--------------------------------

### Create Response with Basic Input

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Use this endpoint to generate responses compatible with OpenAI's Response API format. It supports complex interaction patterns.

```bash
curl -X POST http://localhost:2048/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
    "model": "gemini-2.5-flash",
    "input": "解释什么是RESTful API"
  }'
```

--------------------------------

### Switch to Next Account

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Manually switch to the next available account in the list. Requires authentication and JSON content.

```bash
curl -X PUT http://localhost:2048/api/accounts/current \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{}'
```

--------------------------------

### OpenAI 兼容 API 图像生成

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/docs/zh/api-examples.md

使用 gemini-2.5-flash-image 模型通过 chat/completions 端点生成图像。支持流式和非流式请求。

```bash
curl -X POST http://localhost:7860/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key-1" \
  -d '{
    "model": "gemini-2.5-flash-image",
    "messages": [
      {
        "role": "user",
        "content": "生成一只小猫"
      }
    ],
    "stream": false
  }'
```

```bash
curl -X POST http://localhost:7860/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key-1" \
  -d '{
    "model": "gemini-2.5-flash-image",
    "messages": [
      {
        "role": "user",
        "content": "生成一只小猫"
      }
    ],
    "stream": true
  }'
```

--------------------------------

### Update to Latest Version

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/README.md

Update your local deployment to the latest version by pulling changes and reinstalling dependencies.

```bash
git pull
npm install
```

--------------------------------

### Check for New Version

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

This endpoint checks if a new version of the system is available. Requires authentication.

```bash
curl http://localhost:2048/api/version/check \
  -H "Authorization: Bearer your-api-key"
```

--------------------------------

### Gemini 原生 API 文本生成

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/docs/zh/api-examples.md

使用 Gemini 原生 generateContent 端点。流式响应需在 URL 中添加 alt=sse 参数。

```bash
curl -X POST http://localhost:7860/v1beta/models/gemini-2.5-flash-lite:generateContent \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key-1" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {
            "text": "你好，最近怎么样？"
          }
        ]
      }
    ]
  }'
```

```bash
curl -X POST http://localhost:7860/v1beta/models/gemini-2.5-flash-lite:streamGenerateContent?alt=sse \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key-1" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {
            "text": "写一首关于秋天的诗"
          }
        ]
      }
    ]
  }'
```

--------------------------------

### Responses API 调用

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/docs/zh/api-examples.md

使用 v1/responses 端点进行交互，支持文本输入和结构化消息输入。

```bash
curl -X POST http://localhost:7860/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key-1" \
  -d '{
    "model": "gemini-2.5-flash-lite",
    "input": "请用三句话总结函数式编程的核心思想。",
    "stream": false
  }'
```

```bash
curl -X POST http://localhost:7860/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key-1" \
  -d '{
    "model": "gemini-2.5-flash-lite",
    "input": [
      {
        "role": "user",
        "content": [
          {
            "type": "input_text",
            "text": "写一首关于秋天的短诗。"
          }
        ]
      }
    ],
    "stream": true
  }'
```

--------------------------------

### OpenAI 兼容 API 文本生成

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/docs/zh/api-examples.md

使用 OpenAI 兼容的 chat/completions 端点进行文本生成。支持通过设置 stream 参数切换流式响应。

```bash
curl -X POST http://localhost:7860/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key-1" \
  -d '{
    "model": "gemini-2.5-flash-lite",
    "messages": [
      {
        "role": "user",
        "content": "你好，最近怎么样？"
      }
    ],
    "stream": false
  }'
```

```bash
curl -X POST http://localhost:7860/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key-1" \
  -d '{
    "model": "gemini-2.5-flash-lite",
    "messages": [
      {
        "role": "user",
        "content": "写一首关于秋天的诗"
      }
    ],
    "stream": true
  }'
```

--------------------------------

### Switch to Specific Account

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Switch to a specific account by providing its index in the request body. Requires authentication and JSON content.

```bash
curl -X PUT http://localhost:2048/api/accounts/current \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{"targetIndex": 2}'
```

--------------------------------

### Batch Upload Authentication Files

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Upload multiple authentication files in a single request. Requires authentication and JSON content.

```bash
curl -X POST http://localhost:2048/api/files/batch \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
    "files": [
      {"cookies": [...], "localStorage": {...}},
      {"cookies": [...], "localStorage": {...}}
    ]
  }'
```

--------------------------------

### Batch Download Accounts

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Download authentication files for multiple accounts, packaged as a ZIP archive. Requires authentication and JSON content.

```bash
curl -X POST http://localhost:2048/api/accounts/batch/download \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{"indices": [0, 1, 2]}' \
  --output auth_backup.zip
```

--------------------------------

### Run Docker Container from Built Image

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/README.md

Run a Docker container using a locally built image. This is an alternative to pulling directly from a registry.

```bash
docker run -d \
  --name aistudio-to-api \
  -p 7860:7860 \
  -v /path/to/auth:/app/configs/auth \
  -e API_KEYS=your-api-key-1,your-api-key-2 \
  -e TZ=Asia/Shanghai \
  --restart unless-stopped \
  aistudio-to-api
```

--------------------------------

### 配置内层 Nginx 代理

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/docs/zh/nginx-setup.md

在多层代理架构中，内层网关应透传上游的 X-Real-IP 而非覆盖。

```nginx
# 内层 Nginx（内网网关）配置示例
location / {
    proxy_pass http://127.0.0.1:7860;

    # 关键：透传上游的 X-Real-IP，不要用 $remote_addr 覆盖
    proxy_set_header X-Real-IP $http_x_real_ip;
    proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;

    # 其他必要的代理头
    proxy_set_header Host $host;
    proxy_set_header X-Forwarded-Proto $scheme;

    # 超时设置
    proxy_connect_timeout 600s;
    proxy_send_timeout 600s;
    proxy_read_timeout 600s;

    # 禁用缓冲区
    proxy_buffering off;

	# WebSocket 支持（访问 VNC 时需要）
    proxy_http_version 1.1;
    proxy_set_header Upgrade $http_upgrade;
    proxy_set_header Connection "Upgrade";
}
```

--------------------------------

### Gemini 原生 API 图像生成

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/docs/zh/api-examples.md

使用 gemini-2.5-flash-image 模型通过原生端点生成图像。

```bash
curl -X POST http://localhost:7860/v1beta/models/gemini-2.5-flash-image:generateContent \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key-1" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {
            "text": "生成一只小猫"
          }
        ]
      }
    ]
  }'
```

```bash
curl -X POST http://localhost:7860/v1beta/models/gemini-2.5-flash-image:streamGenerateContent?alt=sse \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key-1" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {
            "text": "生成一只小猫"
          }
        ]
      }
    ]
  }'
```

--------------------------------

### Download Authentication File

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Download a specific authentication file by its filename. Requires authentication.

```bash
curl http://localhost:2048/api/files/auth-0.json \
  -H "Authorization: Bearer your-api-key" \
  --output auth-0.json
```

--------------------------------

### Switch Streaming Mode

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Toggle between 'real' and 'fake' streaming modes for responses. Requires authentication and JSON content.

```bash
curl -X PUT http://localhost:2048/api/settings/streaming-mode \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{"mode": "real"}'
```

--------------------------------

### List Available Models

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Retrieve a list of all models supported by the API. This endpoint is useful for discovering available model IDs.

```bash
curl http://localhost:2048/v1/models \
  -H "Authorization: Bearer your-api-key"
```

--------------------------------

### POST /v1beta/models/gemini-2.5-flash-preview-tts:generateContent

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/docs/zh/api-examples.md

Generates audio content from text input. Supports default voices, specific prebuilt voices, and multi-speaker configurations.

```APIDOC
## POST /v1beta/models/gemini-2.5-flash-preview-tts:generateContent

### Description
Generates speech from text. The response returns base64 encoded audio in audio/L16;codec=pcm;rate=24000 format.

### Method
POST

### Endpoint
http://localhost:7860/v1beta/models/gemini-2.5-flash-preview-tts:generateContent

### Request Body
- **contents** (array) - Required - The input text content.
- **generationConfig** (object) - Required - Configuration including responseModalities set to ["AUDIO"] and optional speechConfig.

### Response
#### Success Response (200)
- **audio** (string) - Base64 encoded PCM audio data.
```

--------------------------------

### List Models

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/README.md

Retrieves a list of available models.

```APIDOC
## GET /v1/models

### Description
Lists available models.

### Method
GET

### Endpoint
/v1/models
```

--------------------------------

### Upload Authentication File

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Upload a new authentication file containing cookies and local storage data. Requires authentication and JSON content.

```bash
curl -X POST http://localhost:2048/api/files \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
    "content": {"cookies": [...], "localStorage": {...}}
  }'
```

--------------------------------

### 配置 Nginx 反向代理

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/docs/zh/nginx-setup.md

定义反向代理规则，包括超时设置、流式响应支持及 WebSocket 转发。需将 server_name 替换为实际域名。

```nginx
server {
    listen 80;
    listen [::]:80;  # IPv6 支持
    server_name your-domain.com;  # 替换为你的域名

    # 如果使用 HTTPS，取消注释以下行并配置 SSL 证书
    # listen 443 ssl http2;
    # listen [::]:443 ssl http2;  # IPv6 HTTPS
    # ssl_certificate /path/to/your/certificate.crt;
    # ssl_certificate_key /path/to/your/private.key;

    # 客户端请求体大小的限制（0 = 不限制）
    client_max_body_size 0;

    location / {
        # 反向代理到 Docker 容器
        proxy_pass http://127.0.0.1:7860;

        # X-Real-IP: 传递真实客户端 IP
        proxy_set_header X-Real-IP $remote_addr;

        # X-Forwarded-For: 包含完整的代理链
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;

        # 其他必要的代理头
        proxy_set_header Host $host;
        proxy_set_header X-Forwarded-Proto $scheme;

        # 超时设置（适配长时间运行的 AI 请求）
        proxy_connect_timeout 600s;
        proxy_send_timeout 600s;
        proxy_read_timeout 600s;

        # 禁用缓冲区以支持流式响应
        proxy_buffering off;

	    # WebSocket 支持（访问 VNC 时需要）
        proxy_http_version 1.1;
        proxy_set_header Upgrade $http_upgrade;
        proxy_set_header Connection "Upgrade";
    }
}
```

--------------------------------

### Set Log Display Count

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Configure the maximum number of log entries to display in the web console. Requires authentication and JSON content.

```bash
curl -X PUT http://localhost:2048/api/settings/log-max-count \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{"count": 200}'
```

--------------------------------

### Toggle Debug Mode

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Switch between DEBUG and INFO log levels for system output. Requires authentication.

```bash
curl -X PUT http://localhost:2048/api/settings/debug-mode \
  -H "Authorization: Bearer your-api-key"
```

--------------------------------

### OpenAI Compatible Chat Completions

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

This endpoint allows you to create chat completions using models compatible with the OpenAI Chat Completions API format. It supports standard parameters like model, messages, temperature, and max_tokens, as well as streaming responses and function calling.

```APIDOC
## POST /v1/chat/completions

### Description
Creates a chat completion request, fully compatible with the OpenAI Chat Completions API format. Supports standard parameters, streaming, and function calling.

### Method
POST

### Endpoint
`/v1/chat/completions`

### Request Body
- **model** (string) - Required - The model to use for chat completions (e.g., "gemini-2.5-flash").
- **messages** (array) - Required - A list of message objects representing the conversation history.
  - **role** (string) - Required - The role of the author of the message (e.g., "system", "user", "assistant").
  - **content** (string) - Required - The content of the message.
- **temperature** (number) - Optional - Controls randomness. Lower values make the output more focused and deterministic.
- **max_tokens** (integer) - Optional - The maximum number of tokens to generate in the completion.
- **stream** (boolean) - Optional - Whether to stream back partial message deltas as they are generated.
- **tools** (array) - Optional - A list of tools the model may call.
- **tool_choice** (string or object) - Optional - Controls how the tool is called.

### Request Example (Standard)
```bash
{
  "model": "gemini-2.5-flash",
  "messages": [
    {"role": "system", "content": "你是一个专业的AI助手"},
    {"role": "user", "content": "请解释什么是机器学习"}
  ],
  "temperature": 0.7,
  "max_tokens": 2048,
  "stream": false
}
```

### Request Example (Streaming)
```bash
{
  "model": "gemini-2.5-pro",
  "messages": [
    {"role": "user", "content": "写一首关于春天的诗"}
  ],
  "stream": true
}
```

### Request Example (Function Calling)
```bash
{
  "model": "gemini-2.5-flash",
  "messages": [
    {"role": "user", "content": "北京今天的天气怎么样？"}
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "获取指定城市的天气信息",
        "parameters": {
          "type": "object",
          "properties": {
            "city": {
              "type": "string",
              "description": "城市名称"
            }
          },
          "required": ["city"]
        }
      }
    }
  ],
  "tool_choice": "auto"
}
```

### Response (Success)
- **id** (string) - Unique identifier for the completion.
- **object** (string) - Type of object returned (e.g., "chat.completion").
- **created** (integer) - Unix timestamp of creation.
- **model** (string) - The model used for the completion.
- **choices** (array) - A list of completion choices.
  - **index** (integer) - Index of the choice.
  - **message** (object) - The generated message.
    - **role** (string) - The role of the author (e.g., "assistant").
    - **content** (string) - The content of the message.
  - **finish_reason** (string) - The reason the model stopped generating tokens.

### Response Example (Standard)
```json
{
  "id": "chatcmpl-12345",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gemini-2.5-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "机器学习是一种人工智能的分支..."
      },
      "finish_reason": "stop"
    }
  ]
}
```

### Response Example (Streaming)
```json
{
  "id": "chatcmpl-12345",
  "object": "chat.completion.chunk",
  "created": 1677652288,
  "model": "gemini-2.5-pro",
  "choices": [
    {
      "index": 0,
      "delta": {
        "role": "assistant",
        "content": "春"
      },
      "finish_reason": null
    }
  ]
}
```
```

--------------------------------

### List Gemini Models (Native API Format)

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/README.md

Retrieve a list of available Gemini models using the native Gemini API format.

```http
GET /v1beta/models
```

--------------------------------

### OpenAI Compatible Models List

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Retrieves a list of all available models that can be used with the chat completions endpoint.

```APIDOC
## GET /v1/models

### Description
Retrieves a list of all available models compatible with the OpenAI API format.

### Method
GET

### Endpoint
`/v1/models`

### Parameters
#### Query Parameters
- **api-key** (string) - Required - Your API key for authentication.

### Request Example
```bash
curl http://localhost:2048/v1/models \
  -H "Authorization: Bearer your-api-key"
```

### Response (Success)
- **object** (string) - Type of object returned (e.g., "list").
- **data** (array) - A list of model objects.
  - **id** (string) - The unique identifier of the model.
  - **object** (string) - Type of object (e.g., "model").
  - **created** (integer) - Unix timestamp of model creation.
  - **owned_by** (string) - The owner of the model (e.g., "google").

### Response Example
```json
{
  "object": "list",
  "data": [
    {
      "id": "gemini-2.5-flash",
      "object": "model",
      "created": 1234567890,
      "owned_by": "google"
    },
    {
      "id": "gemini-2.5-pro",
      "object": "model",
      "created": 1234567890,
      "owned_by": "google"
    }
  ]
}
```
```

--------------------------------

### Toggle Force URL Context

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Enable or disable the forced URL context feature. Requires authentication.

```bash
curl -X PUT http://localhost:2048/api/settings/force-url-context \
  -H "Authorization: Bearer your-api-key"
```

--------------------------------

### Google Gemini Native Generate Content Request

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Directly use the Google Gemini native API format for generating content. Include your API key in the URL query parameters.

```bash
curl -X POST "http://localhost:2048/v1beta/models/gemini-2.5-flash:generateContent?key=your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "parts": [
          {"text": "用Python实现一个快速排序算法"}
        ]
      }
    ],
    "generationConfig": {
      "temperature": 0.7,
      "maxOutputTokens": 2048
    }
  }'
```

--------------------------------

### Translate OpenAI Chat Completions to Google Gemini

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Converts OpenAI Chat Completions format to Google Gemini format.

```APIDOC
## POST /api/translate/openai/chat/completions

### Description
Converts OpenAI Chat Completions format to Google Gemini format.

### Method
POST

### Endpoint
/api/translate/openai/chat/completions

### Request Body
- **model** (string) - Required - The model to use for translation.
- **messages** (array) - Required - An array of message objects.
  - **role** (string) - Required - The role of the message author ('system', 'user', 'assistant').
  - **content** (string) - Required - The content of the message.
- **temperature** (number) - Optional - Controls randomness. Lower values make the output more deterministic.
- **max_tokens** (integer) - Optional - The maximum number of tokens to generate.

### Request Example
```json
{
  "model": "gemini-2.5-flash",
  "messages": [
    { "role": "system", "content": "You are a helpful assistant" },
    { "role": "user", "content": "Hello" }
  ],
  "temperature": 0.7,
  "max_tokens": 2048
}
```

### Response
#### Success Response (200)
- **geminiRequest** (object) - The translated request in Google Gemini format.

#### Response Example
```json
{
  "model": "gemini-2.5-flash",
  "messages": [
    { "role": "system", "content": "你是一个助手" },
    { "role": "user", "content": "你好" }
  ],
  "temperature": 0.7,
  "max_tokens": 2048
}
```
```

--------------------------------

### Imagen 图像生成

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/docs/zh/api-examples.md

使用 imagen-4.0-generate-001 模型通过 :predict 端点生成图像。可通过 sampleCount 参数控制生成数量。

```bash
curl -X POST http://localhost:7860/v1beta/models/imagen-4.0-generate-001:predict \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key-1" \
  -d '{
    "instances": [
      {
        "prompt": "机器人手持红色滑板"
      }
    ],
    "parameters": {
      "sampleCount": 1
    }
  }'
```

```bash
curl -X POST http://localhost:7860/v1beta/models/imagen-4.0-generate-001:predict \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key-1" \
  -d '{
    "instances": [
      {
        "prompt": "夕阳下的未来城市，天空中有飞行汽车"
      }
    ],
    "parameters": {
      "sampleCount": 4
    }
  }'
```

--------------------------------

### POST /v1/responses

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Generates responses compatible with OpenAI's Response API format, supporting complex interaction patterns.

```APIDOC
## POST /v1/responses

### Description
Generates responses compatible with OpenAI's Response API format, supporting complex interaction patterns.

### Method
POST

### Endpoint
/v1/responses

### Parameters
#### Request Body
- **model** (string) - Required - The AI model to use for generation.
- **input** (string) - Required - The prompt or input for the AI model.
- **reasoning** (object) - Optional - Configuration for reasoning, e.g., `{"effort": "high"}`.

### Request Example
```json
{
  "model": "gemini-2.5-flash",
  "input": "解释什么是RESTful API"
}
```

### Request Example with Reasoning
```json
{
  "model": "gemini-2.5-pro",
  "input": "设计一个电商系统的数据库架构",
  "reasoning": {
    "effort": "high"
  }
}
```
```

--------------------------------

### Generate Content (Gemini Native API)

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/README.md

Use this endpoint to generate content, images, and speech via the Gemini API. Specify the model name in the URL.

```http
POST /v1beta/models/{model_name}:generateContent
```

--------------------------------

### Chat Completions (OpenAI Compatible)

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/README.md

Send chat completion requests using the OpenAI compatible API. Supports non-streaming, true streaming, and pseudo-streaming responses. Also supports image generation.

```http
POST /v1/chat/completions
```

--------------------------------

### Stream Generate Content (Gemini Native API)

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/README.md

Enable streaming of content, images, and speech generation using the Gemini API. Supports true and pseudo-streaming.

```http
POST /v1beta/models/{model_name}:streamGenerateContent
```

--------------------------------

### Toggle Force Web Search

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Enable or disable the forced web search functionality. Requires authentication.

```bash
curl -X PUT http://localhost:2048/api/settings/force-web-search \
  -H "Authorization: Bearer your-api-key"
```

--------------------------------

### OpenAI Chat Completions API Request

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Send a chat completion request using the OpenAI compatible endpoint. Ensure to replace 'your-api-key' with your actual API key.

```bash
curl -X POST http://localhost:2048/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
    "model": "gemini-2.5-flash",
    "messages": [
      {"role": "system", "content": "你是一个专业的AI助手"},
      {"role": "user", "content": "请解释什么是机器学习"}
    ],
    "temperature": 0.7,
    "max_tokens": 2048,
    "stream": false
  }'
```

--------------------------------

### OpenAI Chat Completions Streaming Request

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Initiate a streaming chat completion request. This is useful for real-time responses. Replace 'your-api-key' with your valid API key.

```bash
curl -X POST http://localhost:2048/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
    "model": "gemini-2.5-pro",
    "messages": [
      {"role": "user", "content": "写一首关于春天的诗"}
    ],
    "stream": true
  }'
```

--------------------------------

### Settings Management Endpoints

Source: https://context7.com/ibuhub/aistudiotoapi/llms.txt

Endpoints for managing various system settings like streaming mode, thinking mode, web search, URL context, debug mode, and log display count.

```APIDOC
## PUT /api/settings/streaming-mode

### Description
Switches between real streaming and fake streaming modes.

### Method
PUT

### Endpoint
/api/settings/streaming-mode

### Parameters
#### Headers
- **Content-Type** (string) - Required - `application/json`
- **Authorization** (string) - Required - Bearer token for authentication.

#### Request Body
- **mode** (string) - Required - The streaming mode to set (`real` or `fake`).

### Request Example
```json
{
  "mode": "real"
}
```

## PUT /api/settings/force-thinking

### Description
Toggles the force thinking mode.

### Method
PUT

### Endpoint
/api/settings/force-thinking

### Parameters
#### Headers
- **Authorization** (string) - Required - Bearer token for authentication.

## PUT /api/settings/force-web-search

### Description
Toggles the force web search feature.

### Method
PUT

### Endpoint
/api/settings/force-web-search

### Parameters
#### Headers
- **Authorization** (string) - Required - Bearer token for authentication.

## PUT /api/settings/force-url-context

### Description
Toggles the force URL context feature.

### Method
PUT

### Endpoint
/api/settings/force-url-context

### Parameters
#### Headers
- **Authorization** (string) - Required - Bearer token for authentication.

## PUT /api/settings/debug-mode

### Description
Switches between DEBUG and INFO log levels.

### Method
PUT

### Endpoint
/api/settings/debug-mode

### Parameters
#### Headers
- **Authorization** (string) - Required - Bearer token for authentication.

## PUT /api/settings/log-max-count

### Description
Sets the maximum number of log entries to display in the web console.

### Method
PUT

### Endpoint
/api/settings/log-max-count

### Parameters
#### Headers
- **Content-Type** (string) - Required - `application/json`
- **Authorization** (string) - Required - Bearer token for authentication.

#### Request Body
- **count** (integer) - Required - The maximum number of logs to display.

### Request Example
```json
{
  "count": 200
}
```
```

--------------------------------

### Docker Compose Configuration

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/README.md

Define the Docker service configuration in a docker-compose.yml file for easier deployment and management. This includes port mapping, volume mounting, and environment variables.

```yaml
name: aistudio-to-api

services:
  app:
    image: ghcr.io/ibuhub/aistudio-to-api:latest
    container_name: aistudio-to-api
    ports:
      # API 服务器端口（如果使用反向代理，强烈建议改成 127.0.0.1:7860）
      - 7860:7860
    restart: unless-stopped
    volumes:
      # 挂载包含认证文件的目录
      - ./auth:/app/configs/auth
    environment:
      # 用于身份验证的 API 密钥列表（使用逗号分隔）
      API_KEYS: your-api-key-1,your-api-key-2
      # 时区设置（可选，默认使用系统时区）
      TZ: Asia/Shanghai
```

--------------------------------

### Interact with Anthropic-compatible API

Source: https://github.com/ibuhub/aistudiotoapi/blob/main/docs/zh/api-examples.md

Send messages to the model using the Anthropic-compatible endpoint, supporting both standard and streaming responses.

```bash
curl -X POST http://localhost:7860/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: your-api-key-1" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "gemini-2.5-flash-lite",
    "max_tokens": 1024,
    "messages": [
      {
        "role": "user",
        "content": "你好，最近怎么样？"
      }
    ],
    "stream": false
  }'
```

```bash
curl -X POST http://localhost:7860/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: your-api-key-1" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "gemini-2.5-flash-lite",
    "max_tokens": 1024,
    "messages": [
      {
        "role": "user",
        "content": "写一首关于秋天的诗"
      }
    ],
    "stream": true
  }'
```